Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantities and degrees of understanding or knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    нож
    -0.17
    alom
    -0.14
    iforn
    -0.14
     spell
    -0.14
     Ñĩи
    -0.14
     transmitted
    -0.13
    iqueta
    -0.13
    ovich
    -0.13
    ighb
    -0.13
    resher
    -0.13
    POSITIVE LOGITS
     about
    0.22
    burgh
    0.16
     About
    0.16
    about
    0.15
    overlay
    0.15
    bung
    0.15
    -about
    0.14
    About
    0.14
    mil
    0.14
     Foley
    0.14
    Act Density 0.077%

    No Known Activations